苹果发布轨迹归一化模型NTM
Normalizing Trajectory Models
苹果新NTM模型用条件归一化流替代传统扩散步骤，少步采样时保持精确似然训练。
苹果研究团队提出轨迹归一化模型(NTM)，将每个反向步骤建模为条件归一化流。NTM结合浅层可逆块与深度并行架构，在保持精确似然训练的同时解决扩散模型在少步采样中的局限性。该模型在生成压缩到少量粗略转换时表现优于现有方法。
Normalizing Trajectory Models
Diffusion-based models decompose sampling into many small Gaussian denoising steps, an assumption that breaks down when generation is compressed to a few coarse transitions. Existing few-step methods address this through distillation, consistency training, or adversarial objectives, but sacrifice the likelihood framework in the process. We introduce Normalizing Trajectory Models (NTM), which models each reverse step as an expressive conditional normalizing flow with exact likelihood training. Architecturally, NTM combines shallow invertible blocks within each step with a deep parallel…
